© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 46876
    Prev
    Next
    INDEX
    Explanations

    references to the molecule "cytokine" and its variations or related terminology in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words starting with cy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sest
    -0.28
    WebpackPlugin
    -0.28
    fp
    -0.26
    iu
    -0.25
    CodedInputStream
    -0.25
     leading
    -0.24
     ::
    -0.23
     near
    -0.23
    abstract
    -0.22
    al
    -0.22
    POSITIVE LOGITS
     Cy
    1.00
     CY
    0.96
     cy
    0.93
    Cy
    0.88
     cytos
    0.78
    Хьажоргаш
    0.76
    ContentAsync
    0.75
    CY
    0.75
     cycl
    0.75
     cyc
    0.74
    Activations Density 0.045%

    No Known Activations